Skip to main content

Kibana MCP server

Kibana is a data visualization and exploration platform for logs, metrics, and time-series analytics built on top of Elasticsearch. With this MCP server, AI agents can create dashboards, build visualizations, explore data, manage spaces, and configure alerts through natural language commands.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

Kibana supports API key authentication for programmatic access. Generate API keys from the Kibana UI with appropriate permissions for your use case.

  • API Key Header: Authorization: ApiKey {encoded_api_key}
  • Where to generate: Kibana > Stack Management > API Keys
  • Permissions: Configure per API key with read/write access to saved objects and specific spaces
  • Alternative: Basic authentication with username and password

Available tools​

The Kibana MCP server exposes dashboard management, visualization creation, data exploration, space management, and alerting APIs.

ToolPurpose
Dashboard ManagementCreate, update, and delete dashboards; manage dashboard layouts; export configurations
Visualization APIBuild charts (bar, line, pie, heat map); manage aggregations; customize visualization settings
Discover & Saved SearchesExplore data with filters; save search queries; export search results; manage index patterns
Spaces & OrganizationCreate and manage spaces; move objects between spaces; configure space-level permissions
Saved ObjectsExport and import dashboards; bulk update objects; resolve import conflicts
Alerting RulesCreate threshold and query-based alerts; configure alert actions; manage alert lifecycle

Tips​

Start with a clear purpose for each dashboard and group related visualizations logically.

Use meaningful titles and descriptions and avoid dashboard clutter with too many panels.

Choose the right visualization type for your data (line for trends, bar for comparison, pie for composition).

Keep aggregations simple and understandable, and use appropriate time ranges.

Create separate index patterns for different data sources and use consistent naming conventions.

Configure the time field correctly for time-series data.

Set meaningful threshold values that reduce alert fatigue.

Test alerts in dev before production.

Use appropriate notification channels for different alert severities.

Include helpful context in alert messages.

Organize spaces by team or business function and limit access based on roles.

Use consistent naming for spaces and document what each space contains.